© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 11491
    Prev
    Next
    INDEX
    Explanations

    stereotypes

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires strongest on infrequent or out‐of‐vocabulary tokens—i.e. unusually rare words or symbols in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ق
    0.82
    নি
    0.79
     Restriction
    0.75
    Announcement
    0.72
    לח
    0.71
    سين
    0.71
     Три
    0.71
    Три
    0.70
    모
    0.70
    мок
    0.70
    POSITIVE LOGITS
     verdes
    0.99
     señalar
    0.98
     salas
    0.98
    atii
    0.95
     vínculos
    0.94
    arnia
    0.93
    homme
    0.92
     dónde
    0.91
     devuelve
    0.91
     acabó
    0.91
    Activations Density 0.000%

    No Known Activations